# SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

arXiv: https://arxiv.org/abs/2605.31433 · HTML: https://mlsanity.com/paper/2605.31433/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Self-play RL for reasoning, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 44 of its 52 references that are in the map.
- First posted on arXiv 29 May 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-play RL for reasoning](https://mlsanity.com/synth/self-play-rl-for-reasoning/)

## Builds on (most cited first, 30 of 44)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment](https://mlsanity.com/paper/2510.07743/) (2025)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)

## Built on by (most cited first, 7 of 7)

- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning](https://mlsanity.com/paper/2607.26873/) (2026)
- [SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2610.11345/) (2026)
- [Self-Play Search Distillation for Large Language Model Reasoning](https://mlsanity.com/paper/2609.30936/) (2026)
- [Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning](https://mlsanity.com/paper/2610.12593/) (2026)
- [Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks](https://mlsanity.com/paper/2610.17609/) (2026)
- [Cowork-Gym: Synthesizing Interactive Work Environments at Scale](https://mlsanity.com/paper/2610.17670/) (2026)

## Abstract (arXiv)

Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or frontier-model judges. We introduce SCOPE, a data-free self-play framework for open-ended tasks that co-evolves two policies: a Challenger that generates document-grounded tasks, and a Solver that answers them through multi-turn retrieval. A frozen copy of the initial model serves as the self-judge, which writes task-specific rubrics from the source document and grades Solver responses against them. Across three 7-8B instruction-tuned models (Qwen2.5, Qwen3, OLMo-3), SCOPE improves open-ended performance by up to +10.4 points on eight benchmarks and matches or exceeds GRPO_data trained on ~9K curated prompts. Although trained only on open-ended tasks, SCOPE also improves held-out short-form QA by up to +13.8 points on seven held-out benchmarks, surpassing GRPO_data on all three models. Ablations show that co-evolving the Challenger is necessary to keep tasks near the Solver's frontier, that gains arise from improvements in both retrieval and synthesis with the relative contribution varying by task, and that rubric generation quality is the bottleneck for self-judging.